Acquisition of intermediate goals for an agent executing multiple tasks

In this paper, an algorithm that acquires the intermediate goals between the initial and goal states is proposed for an agent executing multiple tasks. We demonstrate the algorithm in the problem of rearranging multiple objects. The result shows that the moving distance to transfer the entire objects to their goal configuration is 1/15 of that without using intermediate goals. We experiment using a real robot to confirm that the intermediate goal can be adapted to a real environment. Our experimental results showed that an agent could adapt the intermediate goals, which were acquired in the simulation, to the experimental environment

[1]  Jun Ota,et al.  Region exploration path planning for a mobile robot expressing working environment by grid points , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[2]  Leslie Pack Kaelbling,et al.  Nearly deterministic abstractions of Markov decision processes , 2002, AAAI/IAAI.

[3]  Jun Ota,et al.  Rearrangement planning of multiple movable objects by using real-time search methodology , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[4]  Andrew G. Barto,et al.  Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density , 2001, ICML.

[5]  Minoru Asada,et al.  Multi-controller fusion in multi-layered reinforcement learning , 2001, Conference Documentation International Conference on Multisensor Fusion and Integration for Intelligent Systems. MFI 2001 (Cat. No.01TH8590).

[6]  Akihiro Matsumoto,et al.  Development of an Omni-Directional Mobile Robot with 3 DoF Decoupling Drive Mechanism , 1995 .

[7]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[8]  Sridhar Mahadevan,et al.  Automatic Programming of Behavior-Based Robots Using Reinforcement Learning , 1991, Artif. Intell..

[9]  Akihiro Matsumoto,et al.  Development of an omni-directional mobile robot with 3 DOF decoupling drive mechanism , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[10]  Larry S. Davis,et al.  Multiresolution path planning for mobile robots , 1986, IEEE J. Robotics Autom..

[11]  N. Biggs.  THE TRAVELING SALESMAN PROBLEM A Guided Tour of Combinatorial Optimization , 1986 .

[12]  Leslie Pack Kaelbling,et al.  Hierarchical Learning in Stochastic Domains: Preliminary Results , 1993, ICML.